© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34007
    Prev
    Next
    INDEX
    Explanations

    scientific names of organisms

    np_acts-logits-general · gemini-2.5-flash-lite

    Latin scientific names of species.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects Latin binomial (genus and species) names in scientific nomenclature.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     like
    -1.35
     it
    -1.33
     its
    -1.25
     "
    -1.20
     at
    -1.20
     a
    -1.18
    %).
    -1.09
     This
    -1.07
     this
    -1.05
     metal
    -1.02
    POSITIVE LOGITS
    Pilih
    1.30
    Spesifikasi
    1.29
     majeurs
    1.26
    Tempat
    1.25
     reager
    1.23
    DAFTAR
    1.23
     horrend
    1.16
     kalender
    1.15
     ekst
    1.15
    Enregistrer
    1.14
    Activations Density 0.055%

    No Known Activations